© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 538
    Prev
    Next
    INDEX
    Explanations

    code comments and multilingual reactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     an
    -1.63
     a
    -1.45
     for
    -1.41
    tać
    -1.31
               
    -1.29
    ListNode
    -1.27
     by
    -1.26
     after
    -1.26
     as
    -1.26
         
    -1.26
    POSITIVE LOGITS
    Hmmm
    1.50
     Traducción
    1.48
    Ugh
    1.41
     umożli
    1.34
     interessante
    1.32
     Descubre
    1.32
     potwier
    1.30
     Saludos
    1.30
    の中には
    1.30
     prouver
    1.27
    Activations Density 0.010%

    No Known Activations